Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    hazard classification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     न्यूमेरिकल
    0.45
    sein
    0.41
    ewer
    0.41
    oram
    0.40
    anum
    0.40
    wwww
    0.40
     Num
    0.39
    ross
    0.39
    ampunk
    0.39
    allah
    0.38
    POSITIVE LOGITS
     ..$
    0.41
     outro
    0.41
     SOLUTION
    0.40
    ᅢ
    0.40
    搞
    0.39
     educator
    0.38
    MATCH
    0.38
     prejudice
    0.38
    মন
    0.38
     Assy
    0.38
    Act Density 0.000%

    No Known Activations